Meta Segment Anything Model Audio | Hacker News Reader

Meta Segment Anything Model Audio

ai.meta.com

223 pointsmegaman82137 comments

I hope we keep making progress in isolating tracks in music. I love listening to stems of my favorite songs, I find all sorts of neat parts I missed out on. Listening to isolated harmonies is cool too.

It shall also allow to make re-recordings in higher quality of stuff that are impossible to find in good quality. Like that cover that that band played only once at that obscure concert and that was recorded on an old tape. Or many very old reggae songs: although many from Jamaica/Kingston had great recordings (there was know-how and great recording studios there) there's also a shitload of old reggae songs that are just barely listenable to because the recording is so poor (and, no, it's not an artistic choice by the artist: it's just, you know, a crappy recording).

The problem of track isolation is sometimes underconstrained, and so any AI system that does this will probably invent "neat parts" for us to hear that weren't necessarily in the original recording. It feels like using super-resolution models to notice details about your great-grandma's wedding dress.

From the papers I've read, the stem separation models all seem to train off what seems like a fairly small dataset that doesn't have great instrument representation.

I wonder if you could assemble a big corpus of individual solo instruments, then permute a cacophonous mix of them. IIRC the main training dataset is comprised of a limited number of real songs. But I think a model trained on real songs might struggle with more "out there" harmonies and mixes.

For future ML developers: A post like this should include system requirements.

It's not clear from the blog post, the git page, and most other places if this will run on, even in big-O:

* CPU

* 16GB GPU

* 240GB server (of the type most business can afford)

* Meta/Google/Open AI/Anthropic-style data center

Indeed. I've tried to run it locally this but couldn't get it running on my measly gaming-spec workstation.

It's seems you need lot's of ram and vram. Reading the issues on github[1], it does not seem many others have had success in using this effectively:

- someone with a 96 Gb VRAM RTX 6000 Pro had cuda oom issues

- someone somehow made it work on a RTX 4090 somehow, but RTF processing time was 12...

- someone with a RTX 5090 managed to use it, but with clips no longer than 20s

It seems utility of the model for hobbyist with consumer grade cards will be low.

[1]: https://github.com/facebookresearch/sam-audio/issues/24

It realy depends on your runtime environment, but I agree it would be nice to have some references with commonly used setups.

It does, but my comment was "even in big-O."

Environments might mean the difference between e.g. 16GB and 24GB, but not 16GB and 160GB.

Would be great for the hearing impaired and CAPD sufferers when combined with Meta glasses or the like.

very cool idea

As someone recording myself playing music, I've been meaning to see if any of these tools are good enough yet to not only separate vocals from another instrument (acoustic guitar for example), but do so without any loss of fidelity (or least not a perceivable one).

The reason I'm interested in this is because recording with multiple microphones (one on guitar, one on the vocal), has it's own set of problems with phase relationship and bleed between the microphones, which causes issues when mixing.

Being able to capture a singing guitarist with a single microphone placed in just the right spot, but still being able to process the tracks individually (with EQ, compression, reverb, etc), could be really helpful.

Funny that:

- This feature is awesome for sample-based music

- Sample music is not what it was due to difficulties related to legal rights

- This model was probably created by not giving a damn about said rights

This is incredible! I wouldn't have thought it was possible to cleanly separate tracks like that. I wonder to what extent the model is filling in gaps, akin to Samsung's "ultra zoom" moon.

I use moises frequently for track separation for learning songs. It does pretty dang well. I was shocked that the score of moises is ranked way worse than just about everything else, including lalal.ai, which I also used before buying moises. Perhaps lalal.ai has gotten better since I last tried it.

Maybe I'm totally misinterpreting, but the chart I'm looking at says "Net Win Rate of SAM Audio vs. SoTA Separation (text prompted)", so perhaps a lower number means that the alternative model is better?

Now that I go back and read it again I agree with you. Presumably "win rate" means what percent of the time did the SAM model (Meta's new one) beat the other tool over some set of examples.

Can this be used to nuke the laugh tracks?!?

It’s really a shame how popular it was to mar shows with this… I saw a DVD set of a show once with a no-laugh-track version. It sucked because the actors pause for the laughs after each line. This is bad enough with the laugh track in place, but if it’s just dead air it makes every scene feel awkward.

AI can remove those pauses by the actors too so maybe that would work.

I don't even mind awkward pauses. I tried using the laugh track silencer on an episode of Black Adder, and it worked out OK.

Playing with the background I tried to Isolate just the espresso machine and the train sounds in one of their demos and it seemed to fail. Maybe not the desired use case, but I thought it was odd that I could break it so easily on the sample material.

Footsteps worked pretty well when I tried that on the other hand. I wonder if lot of it has to do with how well the model understands what the english description of the sound should sound like...

i do think that’s the case. i tried a few different ways to write x and got meaningfully varied results

super amazing demo performance being able separate out music voice and background noises. do you have to explicitly specify what type of noise to separate?

From my brief testing in the playground, it is not very good. Maybe it needs better prompting than the 1 word examples.

For me it either worked great or not at all. Extracting footsteps, the air conditioner noise, voices, one particular persons voice (identified by gender), all worked great (across multiple clips for most of those).

A few prompts failed almost entirely though, "train noises", "background noise" and "clatter"... so definitely sensitive to either prompting or the kind of noise being extracted.

I tried it with their examples, trying to isolate speech only or background music only, but it seems to produce audio that is near identical to the original.

Would be interesting to leverage the non spoken/environment noises to guide what level of detail and style of speech a chatbot replied with, for instance being more casual, gentle, with a touch more detail if in a quiet home/office environment, but more curt and concise with emphasized diction if the person is traveling, such as in a noisy train concourse. People tend to do that subconsciously but bots ignorantly wittering on can be annoying and hard to use because they miss the cues.

can i use this to remove all stupid tiktok music from videos?

mSAMA haha, get it

How about they fix their MusicGEN model on hugging face first.

[flagged]

That’s pretty much been the story since the Neolithic revolution though?

"Don't be curmudgeonly. Thoughtful criticism is fine, but please don't be rigidly or generically negative."

"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

https://news.ycombinator.com/newsguidelines.html

Basically the same thing musicians said about the synth and music made by computers back in the day

100%. The music world has gone through the "but what will we do now?" at least 6-7 times. Music videos ("video killed the radio star"), sampling, the DAW (and time aligning), home studios, auto tune, plugins and amp simulators, napster/piracy, etc, etc.

> napster/piracy

This one rankles me because of a) the benefits piracy has (third world consumers can now discover you, for starters) and b) the absolute bad faith way in which the industry acts, screwing over artists, unethically going after Pirate Bay by making it into a trade war with Sweden (I think)

Reply on news.ycombinator.com